Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, but the description adds a full error contract: failures never raise protocol errors and instead return {"error": ...} with a concrete example, plus explicit retry safety. It also discloses the default 50/30/20 behavior and the exact shape of a typical response, which annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then defaults, example output, usage guidance, and error behavior in a compact block. Every sentence carries information, though the literal JSON example and the 'FREE' marker are slightly bulky for the value they add.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no prose explanation, yet the description still previews the response shape. Usage, alternatives, defaults, error handling, and retry safety are all covered for a simple four-parameter read-only tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds meaning by framing the three percentage parameters as the 50/30/20 default that is 'fully customizable' and showing a concrete input-to-output example. It still doesn't restate the sum-to-100 constraint in the description, leaving that to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Split monthly income into needs/wants/savings buckets with weekly equivalents') and names the sibling it is not for (savings_goal). An agent can distinguish it from tip_split and savings_goal without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit positive trigger ('Use when monthly income needs allocating across buckets') and an explicit exclusion with the alternative named ('Not for how long a target takes to reach (savings_goal)'). No inference required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.